MCP server · Developer tools
Code Sanitizer MCP server
by notasandy
Lets your AI review code for bugs, security holes and SQL injections, and write tests or reports.
This is a small helper that turns your AI assistant into a strict code reviewer. You paste in some code, and it points out bugs, security problems and risky lines, with a score and suggested fixes. It is handy if you write or review code and want a second pair of eyes before you ship something.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill, in this case the skill of reviewing code. You connect it once to Claude Desktop, Cursor, VS Code or Claude Code, and from then on your AI can send your code to this helper, which passes it to an AI service called Groq and brings back a review. You just ask in normal words, and the helper does the technical part behind the scenes.
What this MCP server does
You ask your AI something like review this code for security problems. Your AI sends the code to this helper, which forwards it to Groq, a service that runs a large language model. Groq reads the code and sends back a list of issues with severity, line numbers and suggested fixes, plus a score from 0 to 100. Your AI shows you that list in the chat, and you can ask follow-up questions or ask for tests and an HTML report.
Click to zoomWhat you can do with it
- Review a piece of code for bugs and security issues
- Spot SQL injection and other risky patterns
- Compare two versions of code and see if things got better or worse
- Explain what a piece of code does at junior, middle or senior level
- Generate tests for a function in pytest, jest or go test
- Analyze a whole file from your computer
- Build an HTML report from any analysis result
Try asking your AI
- “Review this code for vulnerabilities: def get_user(user_id): query = f"SELECT * FROM users WHERE id = {user_id}”
- “Explain this function step by step for a junior developer”
- “Compare these two versions of my code and tell me if the refactor made it better”
- “Generate tests for this function, including edge cases”
What it gives back to you
You get back a short summary, a score from 0 to 100, and a list of issues with severity, line number, a plain description and a suggested fix. There are also warnings and general suggestions. For tests, you get ready-to-run test code, and for reports you get an HTML file you can open in a browser.
Before you start
What you need
- A free Groq API key from console.groq.com/keys (no credit card needed)
- The uvx tool, which you can install with pip install uv
- Claude Desktop, Cursor, VS Code or Claude Code CLI to connect it to
Good to know
Your code is sent to the Groq service for review, so do not paste secrets, passwords or private company code you are not allowed to share.
Install it with your AI
Add Code Sanitizer MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Code Sanitizer MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers, students and anyone who reviews or writes code and wants a quick automated check before sharing it.
